© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168889
    Prev
    Next
    INDEX
    Explanations

    introducing factual statements or definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    after noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    N
    0.48
    앵
    0.43
    lin
    0.42
     safegu
    0.41
     accustomed
    0.41
     OCTOBER
    0.40
    crafted
    0.40
    싯
    0.39
     December
    0.39
    썬
    0.38
    POSITIVE LOGITS
    DataReader
    0.55
     détecter
    0.54
     جهت
    0.52
     thảo
    0.52
     démontrer
    0.50
    ခြ
    0.49
     débar
    0.47
     ዘዴ
    0.47
     memperoleh
    0.47
     detección
    0.46
    Activations Density 0.001%

    No Known Activations